Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4232 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.4459. Min Range: -2.4459

Max Act: 2.4459. Min Act: -0.0000

Data Index: 786162 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 2.4459. Min Range: -2.4459

Max Act: 2.2435. Min Act: -0.0000

Data Index: 1098152 (C4 (Web Text))

Max Activating Token Index: 986

Text #2

Max Range: 2.4459. Min Range: -2.4459

Max Act: 2.1794. Min Act: -0.0000

Data Index: 1132620 (C4 (Web Text))

Max Activating Token Index: 917

Text #3

Max Range: 2.4459. Min Range: -2.4459

Max Act: 2.1206. Min Act: -0.0000

Data Index: 981342 (C4 (Web Text))

Max Activating Token Index: 891

Text #4

Max Range: 2.4459. Min Range: -2.4459

Max Act: 2.0740. Min Act: -0.0000

Data Index: 866259 (C4 (Web Text))

Max Activating Token Index: 715

Text #5

Max Range: 2.4459. Min Range: -2.4459

Max Act: 2.0469. Min Act: -0.0000

Data Index: 427022 (C4 (Web Text))

Max Activating Token Index: 888

Text #6

Max Range: 2.4459. Min Range: -2.4459

Max Act: 2.0337. Min Act: -0.0000

Data Index: 1138055 (C4 (Web Text))

Max Activating Token Index: 467

Text #7

Max Range: 2.4459. Min Range: -2.4459

Max Act: 2.0056. Min Act: -0.0000

Data Index: 642889 (C4 (Web Text))

Max Activating Token Index: 479

Text #8

Max Range: 2.4459. Min Range: -2.4459

Max Act: 1.8878. Min Act: -0.0000

Data Index: 465286 (C4 (Web Text))

Max Activating Token Index: 352

Text #9

Max Range: 2.4459. Min Range: -2.4459

Max Act: 1.8822. Min Act: -0.0000

Data Index: 626561 (C4 (Web Text))

Max Activating Token Index: 217

Text #10

Max Range: 2.4459. Min Range: -2.4459

Max Act: 1.9732. Min Act: -0.0000

Data Index: 1109748 (C4 (Web Text))

Max Activating Token Index: 601

Text #11

Max Range: 2.4459. Min Range: -2.4459

Max Act: 1.8205. Min Act: -0.0000

Data Index: 490768 (C4 (Web Text))

Max Activating Token Index: 755

Text #12

Max Range: 2.4459. Min Range: -2.4459

Max Act: 1.9142. Min Act: -0.0000

Data Index: 464340 (C4 (Web Text))

Max Activating Token Index: 725

Text #13

Max Range: 2.4459. Min Range: -2.4459

Max Act: 1.8528. Min Act: -0.0000

Data Index: 322675 (C4 (Web Text))

Max Activating Token Index: 561

Text #14

Max Range: 2.4459. Min Range: -2.4459

Max Act: 1.8680. Min Act: -0.0000

Data Index: 1161005 (C4 (Web Text))

Max Activating Token Index: 532

Text #15

Max Range: 2.4459. Min Range: -2.4459

Max Act: 1.8536. Min Act: -0.0000

Data Index: 384777 (C4 (Web Text))

Max Activating Token Index: 943

Text #16

Max Range: 2.4459. Min Range: -2.4459

Max Act: 1.7446. Min Act: -0.0000

Data Index: 435520 (C4 (Web Text))

Max Activating Token Index: 187

Text #17

Max Range: 2.4459. Min Range: -2.4459

Max Act: 1.9435. Min Act: -0.0000

Data Index: 832113 (C4 (Web Text))

Max Activating Token Index: 695

Text #18

Max Range: 2.4459. Min Range: -2.4459

Max Act: 1.8383. Min Act: -0.0000

Data Index: 360714 (C4 (Web Text))

Max Activating Token Index: 843

Text #19

Max Range: 2.4459. Min Range: -2.4459

Max Act: 1.8268. Min Act: -0.0000

Data Index: 614378 (C4 (Web Text))

Max Activating Token Index: 336